Triple
T5233746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isidore Miller |
E118168
|
entity |
| Predicate | effectOfEvent |
P53074
|
FINISHED |
| Object | business devastated by the Great Depression |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: business devastated by the Great Depression | Statement: [Isidore Miller, effectOfEvent, business devastated by the Great Depression]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOfEvent Context triple: [Isidore Miller, effectOfEvent, business devastated by the Great Depression]
-
A.
eventEffect
chosen
Indicates the resulting change, outcome, or consequence that one event has on another state, entity, or event.
-
B.
eventInfluencedBy
Indicates that an event occurs or unfolds in a way that is causally or significantly affected by another entity, factor, or prior event.
-
C.
impactEvent
Indicates that one entity physically strikes or collides with another, producing a resulting effect or change.
-
D.
tookEffect
Indicates that a change, rule, condition, or event became active, operative, or started producing its intended consequences.
-
E.
effectOnSchedule
Indicates how an event, action, or condition changes, disrupts, or influences a planned schedule or timeline.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69bd4466fb8c819083b806a79414d7e4 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b04c03481908d901788ce2c4128 |
completed | March 20, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69bd77bf1ef08190bb3487b3f3ee088c |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:49 p.m.